National Repository of Grey Literature 41 records found  previous11 - 20nextend  jump to record: Search took 0.01 seconds. 
Accuracy Estimates for Surrogate Solutions of Integral Equations by Neural Networks
Kůrková, Věra
Surrogate solutions of integral equations by neural networks are investigated theoretically. Upper bounds on speed of convergence of approximate solutions computable by neural networks with increasing model complexity to exact solutions described by Fredholm theorem are derived.
Modelová složitost při učení na základě vysoce dimensionálních dat
Kůrková, Věra
Model complexity in learning from high dimensional data is estimated using methods of approximation and integration theory.
Mathematical Modelling of Generalization
Kůrková, Věra
Learning with generalization can be modeled using regularization, which was developed for a search of stable solutions of tasks for physics. In learning theory generalization can be understood as a certain kind of stability.
Integral Combinations of Heavisides
Kainen, P.C. ; Kůrková, Věra ; Vogt, A.
Fulltext: content.csg - Download fulltextPDF
Plný tet: v968-06 - Download fulltextPDF
Machine Learning with Generalization Capability
Kůrková, Věra
Generalization capability in learning of artificial neutral networks from examples can be modelled mathematically using regularization, which was developed as a tool for stability of solutions inverse problems.

National Repository of Grey Literature : 41 records found   previous11 - 20nextend  jump to record:
See also: similar author names
1 KURKOVÁ, Veronika
1 Kůrková, Vladimíra
Interested in being notified about new results for this query?
Subscribe to the RSS feed.